Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
48,622 skills from 2,355 repositories · updated 19 hours ago
48,622 skills
- kiro-debuggotalab/cc-sddInvestigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.EngineeringNo warnings★ 3.7K↓ —Also in 7 other repos
- teachbacknotprop/pstackExplain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.OtherNo warnings★ 3.3K↓ —Also in 1 other repo
- you-web-searchdavepoon/buildwithclaudeSearch the live web and read URLs through the You.com MCP server. Use when you need current information beyond training data: recent releases, docs, pricing, news, or any question where facts may have changed. Two endpoints: keyless basic search at https://api.you.com/mcp?profile=free, or full tools with an API key from https://you.com/platform/api-keys.EngineeringNo warnings★ 3.7K↓ —
- in-your-own-wordsbacknotprop/pstackRestate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words.OtherNo warnings★ 3.3K↓ —
- whymichael-denyer/pstack-claudeUse for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.DevOpsNo warnings★ 3.7K↓ —
- neon-postgresneondatabase/agent-skillsGuides and best practices for working with Lakebase Postgres on Neon: connections, pooled vs direct, schema migrations, branching, autoscaling, scale-to-zero, instant restore, read replicas, IP allow lists, logical replication, and Lakebase Search. Use when the work is an existing DATABASE_URL, SQL, schema, inspect, or search. New backends, Auth, files, Functions, and LLM calls go to the parent `neon` skill. Live queries, reactive UIs, and realtime data go to `neon-realtime`. Also use for "@neondatabase/serverless", "@neon/neon-js", "neon inspect db", "semantic search", "vector search", "full-text search", "BM25", or "hybrid search".OfficialDataNo warnings★ 108↓ —Also in 1 other repo
- video-highlightsZJU-REAL/Easel长视频 / 直播录像高光切片：从一条长视频里找出高光片段，切成多条独立短视频，可选转竖版 9:16 + 加字幕。找点两种方式——音频能量峰值（情绪高涨/欢呼/大声处）或转录后由内容判断挑金句段。当用户说 直播切片、高光切片、长视频切短、录像剪精华、切片、高光时刻、把直播剪成短视频、提取精彩片段、长视频找亮点 时使用。基于 shared/scripts/highlight_cut.py（librosa 能量分析）。与 clipify 区别：clipify 专做英文口播找笑点+动态人脸pan，本 SKILL 更通用（中文/直播皆可）、静态转竖版更稳。MediaNo warnings★ 4.3K↓ —
- gsd:shipdavepoon/buildwithclaudeCreate PR, run review, and prepare for merge after verification passesEngineeringNo warnings★ 3.7K↓ —
- interrogatemichael-denyer/pstack-claudeUse for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Adversaries try to break a change or design, and only findings proven by a run survive.TestingNo warnings★ 3.7K↓ —
- fix-merge-conflictsmichael-denyer/pstack-claudeResolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolutionTestingNo warnings★ 3.7K↓ —
- tao-launch-workflowNVIDIA/skillsThe mandatory pre-launch gate and four-verb execution contract for every TAO workflow or action. Invoke BEFORE launching anything side-effecting — AutoML, train, evaluate, inference, export, TensorRT engine generation, or DEFT/application workflows — on any execution platform. Covers platform selection, credentials, image confirmation, dataset intake, preflight, the launch review, job records, monitoring, and failure/retry classification. Trigger phrases include "train this model", "run AutoML", "launch on SLURM/docker/k8s/brev/virtualenv", "evaluate my checkpoint", "start a TAO job".ProductivityNo warnings★ 3.8K↓ —
- nvflare-orientNVIDIA/skillsRoute open-ended NVFLARE advice and only conversion requests whose preliminary source inspection reports unresolved or conflicting ownership; never load this skill merely to inspect a concrete conversion request before selecting its detected framework converter.MarketingNo warnings★ 3.8K↓ —
- golang-observabilitysamber/cc-skills-golangGolang everyday observability — the always-on signals in production. Covers structured logging with slog, Prometheus metrics, OpenTelemetry distributed tracing, continuous profiling with pprof/Pyroscope, server-side RUM event tracking, alerting, and Grafana dashboards. Apply when instrumenting Go services for production monitoring, setting up metrics or alerting, adding OpenTelemetry tracing, correlating logs with traces, migrating legacy loggers (zap/logrus/zerolog) to slog, adding observability to new features, or implementing GDPR/CCPA-compliant tracking with Customer Data Platforms (CDP). Not for temporary deep-dive performance investigation (→ See `samber/cc-skills-golang@golang-benchmark` and `samber/cc-skills-golang@golang-performance` skills).DevOpsNo warnings★ 3.7K↓ —
- doca-bare-metal-deploymentNVIDIA/skillsRunning a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueField NIC over PCIe, or bare-metal on BlueField Arm. Use this skill for launching and supervising it (direct, tmux, systemd), and when it "exits 1 right after launch", "systemd keeps restarting it", reports "no matching device on the BF", or the BlueField itself is unhealthy: "bfb-install exited 0 but DPU is dead", "ping 192.168.100.2 works but ssh fails", "host PFs aren't showing netdevs". Refuse service containers under kubelet (doca-container-deployment). Covers PCI/NUMA/CPU/IRQ binding, co-tenant isolation (cgroup-v2/netns/numactl), a seven-layer error taxonomy, platform lifecycle (BFB install, RShim/TMFIFO, host PF rebind, post-BFB recovery) and a six-state BlueField lifecycle classifier. Destructive firmware burn / mlxconfig set requires explicit confirmation via doca-hardware-safety; library APIs, env prep, and build use other skills.DevOpsNo warnings★ 3.8K↓ —
- tao-train-deformable-detrNVIDIA/skillsDeformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Deformable-DETR model. Trigger phrases include "train deformable-detr", "Deformable DETR object detection", "lightweight DETR detector".OtherNo warnings★ 3.8K↓ —
- principle-experience-firstmichael-denyer/pstack-claudeApply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.DesignNo warnings★ 3.7K↓ —
- doca-bf4-deploymentNVIDIA/skillsWARNING: guides IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets); every mutating step is governed by doca-hardware-safety (window, rollback). BlueField-4 only: BlueField-3 bring-up is doca-bf3-deployment. Use this skill for BlueField-4 (BF4) day-1 platform bring-up from the BMC: installing the BlueField/DOCA bundle ISO onto the DPU (Grace, the Arm complex) over UEFI HTTP Boot, PXE, or Redfish Virtual Media; the PLDM platform-firmware update via the Redfish UpdateService and pldmtool; and a Grace Ubuntu image with optional cloud-init. Trigger on BlueField-4/BF4 bring-up phrasings even without "BF4": {bring up my new BlueField-4}, {the BlueField ISO will not boot over HTTP from the BMC}, {attach BF4 virtual media via Redfish}, {BF4 firmware Task stuck at Running}, {prepare a BlueField-4 host: platform support, version alignment, safest first smoke test}. Route application launch and library APIs to other skills.DevOpsNo warnings★ 3.8K↓ —
- pricing-packaging-planneraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "plan launch pricing", "design pricing tiers / packaging", or "set up a launch discount / early-bird offer"; produces a launch pricing and packaging plan — tier structure and naming, a value-to-price map aligned to the message house, a launch-offer ladder with a true deadline reason, beta / early-adopter pricing with a post-launch graduation path, and guarantee / refund terms — with every price claim and offer term submitted to memory/events/claims.ndjson. Not for the canonical offer / claim record — use offer-claims-registry; not for paid-newsletter subscription economics — use newsletter-monetization-planner; not for ad bidding — use bid-strategy-planner. 发布定价/梯度打包/早鸟优惠/保证设计PlanningNo warnings★ 3K↓ —
- image-enhancerdavepoon/buildwithclaudeImproves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.MediaNo warnings★ 3.7K↓ —
- skill-account-diagnosisZJU-REAL/Easel账号诊断/起号体检：读取已完善的画像 Profile + 近期内容数据，诊断垂直度、定位清晰度、限流降权信号、流量池阶段，给出病因→证据→处方式的起号意见与发布建议。当用户说账号诊断/起号体检/为什么没流量/是不是被限流了/账号定位诊断/起号建议/怎么起号时使用OtherNo warnings★ 4.3K↓ —
- offensive-wpa-enterpriseSnailSploit/Claude-RedWPA/WPA2/WPA3-Enterprise (802.1X / EAP) attack methodology — EAP method identification (PEAP-MSCHAPv2, EAP-TTLS, EAP-TLS, EAP-GTC, EAP-PWD, EAP-FAST), evil-twin RADIUS attacks with eaphammer for credential capture, MSCHAPv2 challenge-response cracking, EAP-TLS client certificate theft paths (DPAPI, NDES, AD CS auto-enrollment), supplicant validation bypass (missing server cert validation, missing CN pinning, BYOD misconfigurations), and post-capture pivots into AD via cracked domain credentials. Use for corporate Wi-Fi engagements where the network is 802.1X authenticated.MarketingNo warnings★ 10.2K↓ —
- golang-structs-interfacessamber/cc-skills-golangGolang struct and interface design patterns — composition, embedding, type assertions, type switches, interface segregation, dependency injection via interfaces, struct field tags, and pointer vs value receivers. Use this skill when designing Go types, defining or implementing interfaces, embedding structs or interfaces, writing type assertions or type switches, adding struct field tags for JSON/YAML/DB serialization, or choosing between pointer and value receivers. Also use when the user asks about "accept interfaces, return structs", compile-time interface checks, or composing small interfaces into larger ones.DesignNo warnings★ 3.7K↓ —
- kiro-steeringgotalab/cc-sddManage {{KIRO_DIR}}/steering/ as persistent project knowledgeOtherNo warnings★ 3.7K↓ —
- principle-explain-the-numbermichael-denyer/pstack-claudeApply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.OtherNo warnings★ 3.7K↓ —
tao-finetune-clip
NVIDIA/skills
DevOpsUpdated 3 days ago
From the author
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT. This is a single-action model skill; do not use it for an iterative weak-attribute improvement loop that keeps retraining and evaluating until progress stops, which belongs to tao-run-deft-pas.
Install
npx skills add NVIDIA/skills --skill tao-finetune-clip -a claude-code
Installs to .claude/skills/tao-finetune-clip/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance83
Maintenance100
Licence100
Adoption57
Files (23)
- BENCHMARK.md
- SKILL.md
- config/skillspector-baseline.yaml
- evals/evals.json
- references/clip-peft.md
- references/error-patterns.md
- references/pas-metrics.md
- references/skill_info.yaml
- references/spec-param-inference.md
- references/spec_template.yaml
- references/spec_template_deploy.yaml
- references/spec_template_evaluate.yaml
- +11 more